arbiter
JournalsAccount

A perturbation robust test against spurious long memory

Vivien Less & Philipp Sibbertsen

Econometrics and Statistics2025https://doi.org/10.1016/j.ecosta.2025.10.002article
ABDC B
Weight
0.50

Abstract

A semiparametric score-type testing procedure to detect spurious long memory under a perturbed fractional framework is proposed. The test statistic is based on the weighted sum of the partial derivatives of the local Whittle with noise estimator. Consistency of the test against the alternatives of smooth trend and random level shift processes is shown. In addition, the limiting distribution of the test is derived. The finite sample properties of the test are examined in a Monte Carlo simulation study. An empirical example on the squared returns and the realised volatilities from the Verizon Communications stock is conducted, and shows the usefulness of the procedure. • Perturbation robust testing to distinguish true long memory from low-frequency contaminated processes. • Deriving the limiting distribution of the test. • Show good finite sample performance. • Solving the puzzle of receiving contradictory results of the DGP of financial volatility processes when using different proxies.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.1016/j.ecosta.2025.10.002

Or copy a formatted citation

@article{vivien2025,
  title        = {{A perturbation robust test against spurious long memory}},
  author       = {Vivien Less & Philipp Sibbertsen},
  journal      = {Econometrics and Statistics},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1016/j.ecosta.2025.10.002},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

A perturbation robust test against spurious long memory

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.